AI & analytics

Sentiment analysis

Sentiment analysis uses AI to read your reviews, surveys and comments and label the feeling in them as positive, negative or neutral, often by topic.

Updated November 3, 202612 min read

Sentiment analysis at a glance
Also calledOpinion mining, review analysis, emotion AI (for emotion detection)
FieldNatural language processing (NLP), a branch of artificial intelligence
InputReviews, survey comments, social media posts, chats, emails, call transcripts
OutputPolarity (positive / negative / neutral), a score, and often topics and emotions
Main typesDocument-level, sentence-level, aspect-based, emotion detection
MethodsLexicon (rule-based), machine learning, deep learning and large language models
Key early researchPang, Lee & Vaithyanathan (2002); Turney (2002); Hu & Liu (2004)
Common summary metricNet sentiment = (% positive − % negative)
Best forFinding patterns in large volumes of free-text feedback

Key takeaways

  • Sentiment analysis turns thousands of guest comments into data you can count, compare and track over time.
  • Aspect-based sentiment analysis scores each topic in a comment separately, like food, service, wait time and price, which is what makes it so useful when you run restaurants.
  • Modern AI models handle mixed opinions, slang and many languages far better than older keyword lists, though they still slip up now and then.
  • The most valuable output is a trend by topic and location, and reading a sample of the comments behind it keeps your reading of the numbers grounded.
  • How often a topic comes up matters as much as how negative it is. A mild complaint from half your guests usually deserves more attention than a rare, angry one.

What is sentiment analysis?

Sentiment analysis, also known as opinion mining, uses natural language processing (NLP) to understand the feeling behind a piece of text. It reads a review, survey answer or message and works out whether the writer's view is positive, negative or neutral.

More advanced systems go a step further. They pick out what the opinion is about, like food, service or price, and how strongly the guest feels about it.

In your restaurant, the text is mostly guest feedback. It includes reviews on Google, Yelp, TripAdvisor and delivery apps, comments from your NPS and CSAT surveys, social media posts and messages to your support team.

Sentiment analysis turns all of that unstructured text into data you can count, compare between locations and follow over time, which makes it a core part of restaurant intelligence.

How sentiment analysis works

A typical sentiment analysis process for guest feedback has six stages:

  1. Collection. Text from every source (review sites, delivery apps, guest surveys, social media and messages) is gathered in one place, like a unified inbox. The location, platform, date and rating come along with it.
  2. Preparation. The system detects the language, removes duplicates and spam, and splits long comments into sentences.
  3. Sentiment detection. Each comment, sentence or topic gets a label (positive, negative, neutral and sometimes mixed), usually with a score.
  4. Topic identification. The system recognizes the topics each comment mentions, like food quality, staff, wait time, cleanliness, price or delivery, and attaches a sentiment to each.
  5. Aggregation. Results are combined by topic, location, channel and period, and summary measures like net sentiment are calculated, so your analytics dashboards can show them by location.
  6. Action. Dashboards, alerts for sudden changes and prioritized lists of comments help your team respond where it matters most and log incidents that need follow-up.

Types of sentiment analysis

Type What it does Example output
Document-level One label for a whole review or comment "Negative"
Sentence-level One label per sentence Sentence 1 positive, sentence 2 negative
Aspect-based (ABSA) A label for each topic mentioned Food: positive, wait time: negative
Emotion detection Identifies specific emotions Frustration, delight, disappointment
Intent detection Identifies what the writer wants or plans Complaint, refund request, won't return
Fine-grained A graded scale with more than three labels Very negative … very positive (e.g. 1–5)

If you run restaurants, aspect-based analysis is usually the most valuable type, because it ties how guests feel to the part of your business responsible. That link is how feedback turns into operational excellence across your locations.

Sentiment analysis example

Take this review: "The ramen was incredible and the staff were lovely, but we waited 45 minutes for a table even though we had a booking."

Method Result What you learn
Star rating only 3 stars Something was partly wrong
Document-level sentiment Mixed / slightly positive Little additional detail
Aspect-based sentiment Food: positive · Staff: positive · Wait time: negative · Reservations: negative Your kitchen and team are performing well, and the booking and seating process needs attention

Repeat that across hundreds of reviews, and the breakdown shows which part of the guest experience drives your ratings at each location. Our operational insights are built around this kind of topic-level view.

Sentiment analysis methods

Method How it works Strengths Limitations
Lexicon-based (rule-based) Scores words from a dictionary of positive and negative terms, with rules for negation and intensity (e.g. VADER, 2014) Simple, fast and transparent, with no training data required Misses context, sarcasm and restaurant-specific meanings
Classical machine learning Models such as Naive Bayes, logistic regression or support vector machines trained on labeled examples Learns from real data and runs efficiently Requires labeled data and struggles with new subjects and long sentences
Deep learning Neural networks that learn the meaning of words and phrases Handles context and word order better Requires more data and computing power, and is harder to explain
Transformer models Pre-trained models such as BERT, fine-tuned for sentiment High accuracy, with good handling of context and negation Fine-tuning and maintenance take effort
Large language models (LLMs) General-purpose models asked to label sentiment, topics and emotions Handle nuance, mixed opinions and many languages, discover topics without a fixed list, and can summarize Need consistency checks, and costs grow with volume

Many feedback platforms now combine several of these methods. Our insights agent, Rockie, applies AI to your guest feedback.

Sentiment analysis topics in restaurant feedback

Topic Typical positive mentions Typical negative mentions
Food quality Fresh, tasty, well seasoned, generous Cold, bland, overcooked, small portions
Service Friendly, attentive, knowledgeable Rude, slow, ignored, forgetful
Wait time Quick, seated straight away Long wait, slow food, late delivery
Order accuracy Got exactly what we ordered Missing items, wrong order
Cleanliness Spotless, clean restrooms Dirty tables, sticky floors
Atmosphere Cozy, lively, good music Too loud, cramped, cold
Value for money Good value, fair prices Overpriced, small for the price
Delivery and packaging Arrived hot, well packed Spilled, soggy, cold on arrival
Booking and seating Easy to book, table ready Booking lost, kept waiting despite a reservation
Digital experience Easy to order online App crashed, payment failed

Sorting your comments into topics like these is the starting point for discovering customer insights you can act on.

Sentiment analysis calculator

This calculator works out net sentiment, a common way to sum up sentiment for a topic, location or period. It's the percentage of positive mentions minus the percentage of negative ones, and like NPS, it runs from -100 to +100.

Tools define net sentiment in slightly different ways, so your comparisons are most reliable when every figure uses the same method.

Some services report sentiment on a continuous scale instead. Google Cloud Natural Language, for example, gives each text a score from -1.0 to 1.0 and a separate magnitude that reflects the overall strength of emotion.

+42

62% positive, 18% neutral and 20% negative, from 500 mentions.

Net sentiment tells you the most when you calculate it per topic. Your brand might score +60 on food and −15 on wait time, which says far more than a single overall number would.

How restaurants use sentiment analysis

  • Early warning. A rise in negative mentions of wait time at one location shows up weeks before that location's star rating starts to fall. We explored that idea in our post on predictive CX.
  • Prioritized replies. The most negative or emotional comments can rise to the top, so they get a fast, personal response as part of your online reputation management. An AI review manager can draft those replies.
  • Location comparisons. A per-location view, like an operator report, shows which locations are strong on service and weak on food, or the reverse. You can then share what your best locations do well.
  • Measuring change. Sentiment shows whether a new menu, recipe, staffing change or delivery partner actually changed how guests talk about you, and it complements your restaurant data analytics.
  • Explaining scores. When NPS or CSAT falls, you can trace the drop to the topics guests mention most often in their comments.
  • Menu insight. Tracking how often each dish comes up, and how guests feel about it, informs your menu decisions and menu engineering.
  • Guest recovery. Strongly negative comments flag guests worth contacting, and a customer recovery workflow helps you win them back.
  • Incident tracking. Recurring complaints about hygiene, safety or order errors can be logged as incidents. The Mr. Pickle's case study describes a brand that cut incidents by 46%.
  • Competitor benchmarking. Public reviews of nearby competitors show where guests see them as stronger or weaker than you.

Accuracy and limitations of sentiment analysis

Sentiment analysis is never perfect, partly because people also disagree about the sentiment of many comments. These are the challenges you'll run into most:

  • Sarcasm and irony. "Great, another 40-minute wait" uses a positive word to express a negative experience.
  • Negation and contrast. A phrase like "Not bad at all" expresses approval. A sentence that starts "The food was good, but…" usually leads into a complaint.
  • Restaurant-specific meanings. "Hot" is a compliment for soup and a complaint about a dining room, and "spicy" can be either praise or criticism.
  • Very short text. Comments like "Ok", "fine" or a single emoji carry little reliable signal.
  • Mixed opinions. Many reviews praise some things and criticize others, and a single label can hide that.
  • Language and dialect. Slang, local expressions and comments that mix languages are harder for some systems.
  • Comparisons. A phrase like "Better than the other branch" needs context to interpret.
  • Fake and spam reviews. These skew your results unless you filter them out first.

How to evaluate a sentiment analysis tool

Testing a tool on your own data gives you a far clearer picture than any vendor demo.

  1. A test on your own comments. Labeling a few hundred real comments yourself and comparing them with the tool's results shows how well it understands your guests.
  2. Topic accuracy. For restaurants, getting topics like "wait time" or "order accuracy" right matters more than the overall label.
  3. Every language you operate in. Accuracy can differ between languages, so each of your markets deserves a quick check.
  4. The nature of the mistakes. Errors on sarcasm or mixed reviews are expected. Errors on clear complaints are a warning sign.
  5. Traceability. Your managers should be able to click through from any chart to the original comments. Knowing how an AI agent sees your data also helps your team trust its conclusions.
  6. Consistency over time. The same comment should get the same result next month. Otherwise, your trends become unreliable.

Best sentiment analysis tools for restaurants

For a restaurant brand, the most useful sentiment analysis tool reads feedback from all your channels, understands restaurant-specific topics and reports by location. It also helps when the analysis sits next to the tools your team uses to reply to guests.

ToolBest known for
MomosBest pickOur Guest AI Platform for multi-location restaurants. Reviews, surveys and messages are sorted by topic and sentiment in one Unified Inbox, with AI-drafted replies and recovery offers built in.
MedalliaEnterprise experience management with text analytics across surveys, reviews and contact center feedback
QualtricsExperience management platform whose Text iQ analytics categorizes open-text survey feedback
ChatmeterLocal brand reputation management with review and sentiment analytics for multi-location brands
ReviewTrackersReview monitoring and analytics across review sites, now part of InMoment

The right choice depends on your channels and how much feedback you receive. Before you decide, it's worth testing two or three tools on a sample of your own reviews.

Common sentiment analysis mistakes

  • Treating the score as final. Sentiment scores show you where to look, and the comments themselves give you the full picture. Reading them is how teams move from dashboard fatigue to clarity.
  • Measuring only overall sentiment. Without topics, the analysis rarely shows which part of your business needs attention.
  • Overlooking volume. How often a topic comes up matters as much as how negative it is.
  • Mixing sources without labels. Delivery app reviews, Google reviews and survey comments come from different guests in different situations, so being able to tell them apart makes your results easier to read.
  • Skipping spam and fake-review filtering. Unfiltered fake reviews can skew the results for a location.

History of sentiment analysis

Interest in detecting opinions automatically grew fast in the early 2000s, as online reviews gave researchers large collections of opinionated writing to study.

Two papers from 2002 are often seen as the start of the field. Bo Pang, Lillian Lee and Shivakumar Vaithyanathan classified movie reviews with machine learning in "Thumbs up? Sentiment Classification using Machine Learning Techniques". Peter Turney classified reviews based on the meaning of their words and phrases in "Thumbs Up or Thumbs Down?".

In 2004, Minqing Hu and Bing Liu published "Mining and Summarizing Customer Reviews". Their method picked out the product features customers mentioned and the opinion expressed about each one, which laid the groundwork for aspect-based analysis.

In 2012, Bing Liu published the book Sentiment Analysis and Opinion Mining. It brought document-level classification, aspect-based analysis, sentiment lexicons and opinion spam detection together in one reference for the field.

Restaurant reviews later became one of the field's standard test sets. The SemEval research competitions from 2014 to 2016 included aspect-based sentiment tasks built on restaurant reviews, starting with SemEval-2014 Task 4, with aspects like food, service, price and ambience.

Since then, methods have moved from word lists to statistical machine learning, then to deep learning, and from 2018 onward to transformer models like BERT. Today's large language models (LLMs) can analyze sentiment and topics with little or no task-specific training.

Frequently asked questions

What is aspect-based sentiment analysis?

Aspect-based sentiment analysis (ABSA) finds each topic mentioned in a piece of text and scores it separately. A comment like "Great pasta, but we waited 40 minutes" becomes positive on food and negative on wait time. That's far more useful than a single "mixed" label.

How accurate is sentiment analysis?

It depends on the method, the subject and the language. Even people often disagree about a comment's sentiment, so no system is perfect. Modern models handle most everyday reviews well, while sarcasm, very short comments and slang are still harder. The surest way to judge a tool is to test it on a sample of your own reviews.

Why would a restaurant use sentiment analysis?

A multi-location brand can get thousands of reviews, survey comments and messages each month, far more than any team can read. Sentiment analysis sorts them for you, so you can see which issues are growing, where, and since when. The Condado Tacos case study shows how one brand built chain-wide guest intelligence from its feedback.

Isn't a star rating enough?

A star rating shows how a guest felt overall, and the text explains why. Two 3-star reviews can describe completely different problems, and a 5-star review can still mention a complaint. Sentiment analysis reads the text so you can see what's driving the rating.

What is a net sentiment score?

Net sentiment is a common summary score. It's the percentage of positive mentions minus the percentage of negative ones, which gives a value from -100 to +100, and it's usually calculated per topic, location or period. Tools define it slightly differently, so it's worth checking how yours works.

Can sentiment analysis detect emotions like anger?

Yes. Emotion detection goes beyond positive and negative to pick out feelings like anger, frustration or delight. It helps you decide which replies come first, since an angry guest usually needs a faster response than a mildly disappointed one. Our guide on how to respond to customer feedback covers what to say.

Does sentiment analysis work in languages other than English?

Modern multilingual models work across many languages, including comments that mix two of them. Accuracy can still vary from one language to another, so it's sensible to review the results in each market where you operate.